[dev.simd] all: merge master (4c4cefc) into dev.simd

Merge List:

+ 2025-09-03 4c4cefc19a cmd/gofmt: simplify logic to process arguments
+ 2025-09-03 925a3cdcd1 unicode/utf8: make DecodeRune{,InString} inlineable
+ 2025-09-03 3e596d448f math: rename Modf parameter int to integer
+ 2025-09-02 2a7f1d47b0 runtime: use one more address bit for tagged pointers
+ 2025-09-02 b09068041a cmd/dist: run racebench tests only in longtest mode
+ 2025-09-02 355370ac52 runtime: add comment for concatstring2
+ 2025-09-02 1eec830f54 go/doc: linkify interface methods
+ 2025-08-31 7bba745820 cmd/compile: use generated loops instead of DUFFZERO on loong64
+ 2025-08-31 882335e2cb cmd/internal/obj/loong64: add LDPTR.{W/D} and STPTR.{W/D} instructions support
+ 2025-08-31 d4b17f5869 internal/runtime/atomic: reset wrong jump target in Cas{,64} on loong64
+ 2025-08-31 6a08e80399 net/http: skip redirecting in ServeMux when URL path for CONNECT is empty
+ 2025-08-29 8bcda6c79d runtime/race: add race detector support for linux/riscv64
+ 2025-08-29 8377adafc5 cmd/cgo: split loadDWARF into two parts
+ 2025-08-29 a7d9d5a80a cmd/cgo: move typedefs and typedefList out of Package
+ 2025-08-29 1d459c4357 all: delete more windows/arm remnants
+ 2025-08-29 27ce6e4e26 cmd/compile: remove sign extension before MULW on riscv64
+ 2025-08-29 84b070bfb1 cmd/compile/internal/ssa: make oneBit function generic
+ 2025-08-29 fe42628dae internal/cpu: inline DebugOptions
+ 2025-08-29 94b7d519bd net: update document on limitation of iprawsock on Windows
+ 2025-08-29 ba9e1ddccf testing: allow specify temp dir by GOTMPDIR environment variable
+ 2025-08-29 9f6936b8da cmd/link: disallow linkname of runtime.addmoduledata
+ 2025-08-29 89d41d254a bytes, strings: speed up TrimSpace
+ 2025-08-29 38204e0872 testing/synctest: call out common issues with tests
+ 2025-08-29 252c901125 os,syscall: pass file flags to CreateFile on Windows
+ 2025-08-29 53515fb0a9 crypto/tls: use hash.Cloner
+ 2025-08-28 13bb48e6fb go/constant: fix complex != unknown comparison
+ 2025-08-28 ba1109feb5 net: remove redundant cgoLookupCNAME return parameter
+ 2025-08-28 f74ed44ed9 net/http/httputil: remove redundant pw.Close() call in DumpRequestOut
+ 2025-08-28 a9689d2e0b time: skip TestLongAdjustTimers in short mode on single CPU systems
+ 2025-08-28 ebc763f76d syscall: only get parent PID if SysProcAttr.Pdeathsig is set
+ 2025-08-28 7f1864b0a8 strings: remove redundant "runs" from string.Fields docstring
+ 2025-08-28 90c21fa5b6 net/textproto: eliminate some bounds checks
+ 2025-08-27 e47d88beae os: return nil slice when ReadDir is used with a file on file_windows
+ 2025-08-27 6b837a64db cmd/internal/obj/loong64: simplify buildop
+ 2025-08-27 765905e3bd debug/elf: don't panic if symtab too small
+ 2025-08-27 2ee4b31242 net/http: Ensure that CONNECT proxied requests respect MaxResponseHeaderBytes
+ 2025-08-27 b21867b1a2 net/http: require exact match for CrossSiteProtection bypass patterns
+ 2025-08-27 d19e377f6e cmd/cgo: make it safe to run gcc in parallel
+ 2025-08-27 49a2f3ed87 net: allow zero value destination address in WriteMsgUDPAddrPort
+ 2025-08-26 afc51ed007 internall/poll: remove bufs field from Windows' poll.operation
+ 2025-08-26 801b74eb95 internal/poll: remove rsa field from Windows' poll.operation
+ 2025-08-26 fa18c547cd syscall: sort Windows env block in StartProcess
+ 2025-08-26 bfd130db02 internal/poll: don't use stack-allocated WSAMsg parameters
+ 2025-08-26 dae9e456ae runtime: identify virtual memory layout for riscv64
+ 2025-08-25 25c2d4109f math: use Trunc to implement Modf
+ 2025-08-25 4e05a070c4 math: implement IsInf using Abs
+ 2025-08-25 1eed4f32a0 math: optimize Signbit implementation slightly
+ 2025-08-25 bd71b94659 cmd/compile/internal: optimizing add+sll rule using ALSLV instruction on loong64
+ 2025-08-25 ea55ca3600 runtime: skip doInit of plugins in runtime.main
+ 2025-08-25 9ae2f1fb57 internal/trace: skip async preempt off tests on low end systems
+ 2025-08-25 bbd5342a62 net: fix cgoResSearch
+ 2025-08-25 ed7f804775 os: set full name for Roots created with Root.OpenRoot
+ 2025-08-25 a21249436b internal/poll: use fdMutex to provide read/write locking on Windows
+ 2025-08-24 44c5956bf7 test/codegen: add Mul2 and DivPow2 test for loong64
+ 2025-08-24 0aa8019e94 test/codegen: add Mul* test for loong64
+ 2025-08-24 83420974b7 test/codegen: add sqrt* abs and copysign test for loong64
+ 2025-08-23 f2db0dca0b net/http/httptest: redirect example.com requests to server
+ 2025-08-22 d86ec92499 internal/syscall/windows: increase internal Windows O_ flags values
+ 2025-08-22 9d3f7fda70 crypto/tls: fix quic comment typo
+ 2025-08-22 78a05c541f internal/poll: don't pass non-nil WSAMsg.Name with 0 namelen on windows
+ 2025-08-22 52c3f73fda runtime/metrics: improve doc
+ 2025-08-22 a076f49757 os: fix Root.MkdirAll to handle race of directory creation
+ 2025-08-22 98238fd495 all: delete remaining windows/arm code
+ 2025-08-21 1ad30844d9 cmd/asm: process forward jump to PCALIGN
+ 2025-08-21 13c082601d internal/poll: permit nil destination address in WriteMsg{Inet4,Inet6}
+ 2025-08-21 9b0a507735 runtime: remove remaining windows/arm files and comments
+ 2025-08-21 1843f1e9c0 cmd/compile: use zero register instead of specialized *zero instructions on loong64
+ 2025-08-21 e0870a0a12 cmd/compile: simplify zerorange on loong64
+ 2025-08-21 fb8bbe46d5 cmd/compile/internal/ssa: eliminate unnecessary extension operations
+ 2025-08-21 9632ba8160 cmd/compile: optimize some patterns into revb2h/revb4h instruction on loong64
+ 2025-08-21 8dcab6f450 syscall: simplify execve handling on libc platforms
+ 2025-08-21 ba840c1bf9 cmd/compile: deduplication in the source code generated by mknode
+ 2025-08-21 fa706ea50f cmd/compile: optimize rule (x + x) << c to x << c+1 on loong64
+ 2025-08-21 ffc85ee1f1 cmd/internal/objabi,cmd/link: add support for additional riscv64 relocations

Change-Id: I3896f74b1a3cc0a52b29ca48767bb0ba84620f71

6 files changed, 97 insertions, 43 deletions

diff --git a/src/cmd/internal/obj/fips140.go b/src/cmd/internal/obj/fips140.go
index ea36849a21..da18b64178 100644
--- a/src/cmd/internal/obj/fips140.go
+++ b/src/cmd/internal/obj/fips140.go
@@ -196,14 +196,8 @@ func EnableFIPS() bool {
 	// Perhaps the default should be changed back to -buildmode=exe,
 	// after which we could remove this case, but until then,
 	// skip FIPS on windows-386.
-	//
-	// We don't know whether arm works, because it is too hard to get builder
-	// time to test it. Disable since it's not important right now.
-	if buildcfg.GOOS == "windows" {
-		switch buildcfg.GOARCH {
-		case "386", "arm":
-			return false
-		}
+	if buildcfg.GOOS == "windows" && buildcfg.GOARCH == "386" {
+		return false
 	}
 
 	// AIX doesn't just work, and it's not worth fixing.
diff --git a/src/cmd/internal/obj/loong64/a.out.go b/src/cmd/internal/obj/loong64/a.out.go
index f5d20cfabe..8e651cdfef 100644
--- a/src/cmd/internal/obj/loong64/a.out.go
+++ b/src/cmd/internal/obj/loong64/a.out.go
@@ -666,6 +666,10 @@ const (
 	ABSTRPICKW
 	ABSTRPICKV
 
+	// 2.2.5.3
+	AMOVWP
+	AMOVVP
+
 	// 2.2.5.4. Prefetch Instructions
 	APRELD
 	APRELDX
diff --git a/src/cmd/internal/obj/loong64/anames.go b/src/cmd/internal/obj/loong64/anames.go
index 67b5f2fc80..c629553d55 100644
--- a/src/cmd/internal/obj/loong64/anames.go
+++ b/src/cmd/internal/obj/loong64/anames.go
@@ -202,6 +202,8 @@ var Anames = []string{
 	"BSTRINSV",
 	"BSTRPICKW",
 	"BSTRPICKV",
+	"MOVWP",
+	"MOVVP",
 	"PRELD",
 	"PRELDX",
 	"CRCWBW",
diff --git a/src/cmd/internal/obj/loong64/asm.go b/src/cmd/internal/obj/loong64/asm.go
index ffd1177350..1b982f6c86 100644
--- a/src/cmd/internal/obj/loong64/asm.go
+++ b/src/cmd/internal/obj/loong64/asm.go
@@ -212,6 +212,8 @@ var optab = []Optab{
 	{AMOVV, C_REG, C_NONE, C_NONE, C_TLS_LE, C_NONE, 53, 16, 0, 0},
 	{AMOVB, C_REG, C_NONE, C_NONE, C_TLS_LE, C_NONE, 53, 16, 0, 0},
 	{AMOVBU, C_REG, C_NONE, C_NONE, C_TLS_LE, C_NONE, 53, 16, 0, 0},
+	{AMOVWP, C_REG, C_NONE, C_NONE, C_SOREG, C_NONE, 73, 4, 0, 0},
+	{AMOVWP, C_REG, C_NONE, C_NONE, C_LOREG, C_NONE, 73, 4, 0, 0},
 
 	{AMOVW, C_LAUTO, C_NONE, C_NONE, C_REG, C_NONE, 36, 12, REGSP, 0},
 	{AMOVWU, C_LAUTO, C_NONE, C_NONE, C_REG, C_NONE, 36, 12, REGSP, 0},
@@ -233,6 +235,8 @@ var optab = []Optab{
 	{AMOVV, C_TLS_LE, C_NONE, C_NONE, C_REG, C_NONE, 54, 16, 0, 0},
 	{AMOVB, C_TLS_LE, C_NONE, C_NONE, C_REG, C_NONE, 54, 16, 0, 0},
 	{AMOVBU, C_TLS_LE, C_NONE, C_NONE, C_REG, C_NONE, 54, 16, 0, 0},
+	{AMOVWP, C_SOREG, C_NONE, C_NONE, C_REG, C_NONE, 74, 4, 0, 0},
+	{AMOVWP, C_LOREG, C_NONE, C_NONE, C_REG, C_NONE, 74, 4, 0, 0},
 
 	{AMOVW, C_SACON, C_NONE, C_NONE, C_REG, C_NONE, 3, 4, REGSP, 0},
 	{AMOVV, C_SACON, C_NONE, C_NONE, C_REG, C_NONE, 3, 4, REGSP, 0},
@@ -438,8 +442,6 @@ var optab = []Optab{
 	{obj.ANOP, C_FREG, C_NONE, C_NONE, C_NONE, C_NONE, 0, 0, 0, 0},
 	{obj.ADUFFZERO, C_NONE, C_NONE, C_NONE, C_BRAN, C_NONE, 11, 4, 0, 0}, // same as AJMP
 	{obj.ADUFFCOPY, C_NONE, C_NONE, C_NONE, C_BRAN, C_NONE, 11, 4, 0, 0}, // same as AJMP
-
-	{obj.AXXX, C_NONE, C_NONE, C_NONE, C_NONE, C_NONE, 0, 4, 0, 0},
 }
 
 var atomicInst = map[obj.As]uint32{
@@ -1303,31 +1305,27 @@ func buildop(ctxt *obj.Link) {
 		return
 	}
 
-	var n int
-
-	for i := 0; i < C_NCLASS; i++ {
-		for n = 0; n < C_NCLASS; n++ {
-			if cmp(n, i) {
-				xcmp[i][n] = true
+	for i := range C_NCLASS {
+		for j := range C_NCLASS {
+			if cmp(j, i) {
+				xcmp[i][j] = true
 			}
 		}
 	}
-	for n = 0; optab[n].as != obj.AXXX; n++ {
-	}
-	slices.SortFunc(optab[:n], ocmp)
-	for i := 0; i < n; i++ {
-		r := optab[i].as
-		r0 := r & obj.AMask
-		start := i
-		for optab[i].as == r {
-			i++
-		}
-		oprange[r0] = optab[start:i]
-		i--
 
-		switch r {
+	slices.SortFunc(optab, ocmp)
+	for i := 0; i < len(optab); i++ {
+		as, start := optab[i].as, i
+		for ; i < len(optab)-1; i++ {
+			if optab[i+1].as != as {
+				break
+			}
+		}
+		r0 := as & obj.AMask
+		oprange[r0] = optab[start : i+1]
+		switch as {
 		default:
-			ctxt.Diag("unknown op in build: %v", r)
+			ctxt.Diag("unknown op in build: %v", as)
 			ctxt.DiagFlush()
 			log.Fatalf("bad code")
 
@@ -1443,6 +1441,9 @@ func buildop(ctxt *obj.Link) {
 		case AMOVBU:
 			opset(AMOVHU, r0)
 
+		case AMOVWP:
+			opset(AMOVVP, r0)
+
 		case AMUL:
 			opset(AMULU, r0)
 			opset(AMULH, r0)
@@ -1970,6 +1971,10 @@ func OP_16IRR(op uint32, i uint32, r2 uint32, r3 uint32) uint32 {
 	return op | (i&0xFFFF)<<10 | (r2&0x1F)<<5 | (r3&0x1F)<<0
 }
 
+func OP_14IRR(op uint32, i uint32, r2 uint32, r3 uint32) uint32 {
+	return op | (i&0x3FFF)<<10 | (r2&0x1F)<<5 | (r3&0x1F)<<0
+}
+
 func OP_12IR_5I(op uint32, i1 uint32, r2 uint32, i2 uint32) uint32 {
 	return op | (i1&0xFFF)<<10 | (r2&0x1F)<<5 | (i2&0x1F)<<0
 }
@@ -2899,6 +2904,20 @@ func (c *ctxt0) asmout(p *obj.Prog, o *Optab, out []uint32) {
 			o3 = OP_12IRR(c.opirr(ALU52ID), uint32(v>>52), uint32(REGTMP), uint32(REGTMP))
 		}
 		o4 = OP_RRR(c.oprrr(p.As), uint32(REGTMP), uint32(r), uint32(p.To.Reg))
+
+	case 73:
+		v := c.regoff(&p.To)
+		if v&3 != 0 {
+			c.ctxt.Diag("%v: offset must be a multiple of 4.\n", p)
+		}
+		o1 = OP_14IRR(c.opirr(p.As), uint32(v>>2), uint32(p.To.Reg), uint32(p.From.Reg))
+
+	case 74:
+		v := c.regoff(&p.From)
+		if v&3 != 0 {
+			c.ctxt.Diag("%v: offset must be a multiple of 4.\n", p)
+		}
+		o1 = OP_14IRR(c.opirr(-p.As), uint32(v>>2), uint32(p.From.Reg), uint32(p.To.Reg))
 	}
 
 	out[0] = o1
@@ -4032,6 +4051,10 @@ func (c *ctxt0) opirr(a obj.As) uint32 {
 		return 0x0ad << 22
 	case AMOVD:
 		return 0x0af << 22
+	case AMOVVP:
+		return 0x27 << 24 // stptr.d
+	case AMOVWP:
+		return 0x25 << 24 // stptr.w
 	case -AMOVB:
 		return 0x0a0 << 22
 	case -AMOVBU:
@@ -4050,6 +4073,10 @@ func (c *ctxt0) opirr(a obj.As) uint32 {
 		return 0x0ac << 22
 	case -AMOVD:
 		return 0x0ae << 22
+	case -AMOVVP:
+		return 0x26 << 24 // ldptr.d
+	case -AMOVWP:
+		return 0x24 << 24 // ldptr.w
 	case -AVMOVQ:
 		return 0x0b0 << 22 // vld
 	case -AXVMOVQ:
diff --git a/src/cmd/internal/obj/loong64/doc.go b/src/cmd/internal/obj/loong64/doc.go
index 64bb41ae5a..6c8f2618a2 100644
--- a/src/cmd/internal/obj/loong64/doc.go
+++ b/src/cmd/internal/obj/loong64/doc.go
@@ -289,6 +289,34 @@ Note: In the following sections 3.1 to 3.6, "ui4" (4-bit unsigned int immediate)
 
             Go assembly      | instruction Encoding
         ALSLV $4, r4, r5, R6 |      002d9486
+
+5. Note of special memory access instructions
+    Instruction format:
+      MOVWP	offset(Rj), Rd
+      MOVVP	offset(Rj), Rd
+      MOVWP	Rd, offset(Rj)
+      MOVVP	Rd, offset(Rj)
+
+    Mapping between Go and platform assembly:
+               Go assembly      |      platform assembly
+      MOVWP  offset(Rj), Rd     |    ldptr.w  rd, rj, si14
+      MOVVP  offset(Rj), Rd     |    ldptr.d  rd, rj, si14
+      MOVWP  Rd, offset(Rj)     |    stptr.w  rd, rj, si14
+      MOVVP  Rd, offset(Rj)     |    stptr.d  rd, rj, si14
+
+      note: In Go assembly, for ease of understanding, offset is a 16-bit immediate number representing
+            the actual address offset, but in platform assembly, it need a 14-bit immediate number.
+	    si14 = offset>>2
+
+    The addressing calculation for the above instruction involves logically left-shifting the 14-bit
+    immediate number si14 by 2 bits, then sign-extending it, and finally adding it to the value in the
+    general-purpose register rj to obtain the sum.
+
+    For example:
+
+            Go assembly      |      platform assembly
+         MOVWP  8(R4), R5    |      ldptr.w r5, r4, $2
+
 */
 
 package loong64
diff --git a/src/cmd/internal/obj/x86/asm6.go b/src/cmd/internal/obj/x86/asm6.go
index b071bd530d..03718fbb31 100644
--- a/src/cmd/internal/obj/x86/asm6.go
+++ b/src/cmd/internal/obj/x86/asm6.go
@@ -2120,19 +2120,6 @@ func span6(ctxt *obj.Link, s *obj.LSym, newprog obj.ProgAlloc) {
 			c0 := c
 			c = pjc.padJump(ctxt, s, p, c)
 
-			if p.As == obj.APCALIGN || p.As == obj.APCALIGNMAX {
-				v := obj.AlignmentPadding(c, p, ctxt, s)
-				if v > 0 {
-					s.Grow(int64(c) + int64(v))
-					fillnop(s.P[c:], int(v))
-				}
-				p.Pc = int64(c)
-				c += int32(v)
-				pPrev = p
-				continue
-
-			}
-
 			if maxLoopPad > 0 && p.Back&branchLoopHead != 0 && c&(loopAlign-1) != 0 {
 				// pad with NOPs
 				v := -c & (loopAlign - 1)
@@ -2165,6 +2152,18 @@ func span6(ctxt *obj.Link, s *obj.LSym, newprog obj.ProgAlloc) {
 				}
 			}
 
+			if p.As == obj.APCALIGN || p.As == obj.APCALIGNMAX {
+				v := obj.AlignmentPadding(c, p, ctxt, s)
+				if v > 0 {
+					s.Grow(int64(c) + int64(v))
+					fillnop(s.P[c:], int(v))
+				}
+				p.Pc = int64(c)
+				c += int32(v)
+				pPrev = p
+				continue
+			}
+
 			p.Rel = nil
 
 			p.Pc = int64(c)